生成对抗网络医学图像去噪研究综述

doi:10.3969/j.issn.0258-8021.2022.06.010

摘要
图/表
参考文献
相关文章 (15)

全文: PDF (1050 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要医学图像作为辅助医生诊断和治疗的重要手段,其清晰度对临床医疗的重要性不言而喻。生成对抗网络(GAN)独特的对抗训练思想在图像生成任务中展现出强大的学习能力,因其能生成高质量的样本,故在计算机视觉领域的研究前景光明。针对GAN应用于医学图像去噪任务进行概括和总结。首先介绍GAN的基础理论和优缺点;然后对适用于医学图像去噪的GAN的衍生模型进行详细介绍,总结有助于提升GAN医学图像去噪性能的各种损失函数及其作用,以及其他可以嵌套在GAN模型中并对医学图像去噪起辅助作用的深度学习类框架;并总结提升医学图像去噪的GAN网络性能的方法;最后探讨了GAN用于医学图像去噪的应用前景、面临的挑战以及未来可能的研究方向。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	于淼
	许铮铧

关键词 ：生成对抗网络(GAN), 深度学习, 噪声, 医学图像去噪, 损失函数

Abstract：As an important means to assist the detection of diseases and make better diagnostic decisions, the definition of medical image is of great significance for clinical treatment. The unique confrontation training idea of generative adversarial network (GAN) can generate high-quality samples. The success in the field of computer vision makes GAN a bright prospect. In this article, the application of GAN in medical image denoising was reviewed. Firstly, the basic theory, advantages and disadvantages of GAN were introduced. Then, the derivation model of GAN for medical image denoising was introduced in detail, and various loss functions that can help improve the denoising performance of GAN for medical images were summarized. And other deep learning frameworks, which can be nested into the GAN model and play an auxiliary role in medical image denoising, were presented as well. The methods to improve the performance of GAN network for medical image denoising were summarized. Finally, the application prospects, challenges and possible future research directions of GAN in medical image denoising were discussed.

Key words： generative adversarial networks (GANs) deep learning noise medical image denoising loss function

收稿日期: 2021-10-13

PACS:

R318

基金资助:国家自然科学基金青年基金(61906063)

通讯作者: ^*E-mail: xuzhenghua1987@gmail.com

作者简介: ^#中国生物医学工程学会会员

引用本文:

于淼, 许铮铧. 生成对抗网络医学图像去噪研究综述[J]. 中国生物医学工程学报, 2022, 41(6): 724-731.
Yu Miao, Xu Zhenghua. A Review on Generative Adversarial Networks in Medical Image. Chinese Journal of Biomedical Engineering, 2022, 41(6): 724-731.

链接本文:

http://cjbme.csbme.org/CN/10.3969/j.issn.0258-8021.2022.06.010 或 http://cjbme.csbme.org/CN/Y2022/V41/I6/724

[1] Kim H, Lee D. Image denoising with conditional generative adversarial networks (CGAN) in low dose chest images [J]. Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, 2020, 954(8):161914.
[2] Yu Haijun, Wang Shaoyu, Wu Weiwen, et al. Weighted adaptive non-local dictionary for low-dose CT reconstruction [J]. Signal Processing, 2021, 180 (3): 107871.
[3] Kostadin D, Alessandro F, Vladimir K, et al. Image denoising by sparse 3D transform-domain collaborative ltering [J]. IEEE Transactions on Image Processing, 2007, 16(8): 1-16.
[4] Tian Chunwei, Fei Lunke, Zheng Wenxian, et al. Deep learning on image denoising: an overview [J]. Neural Networks, 2020, 131(11): 251-275.
[5] Kostadin D, Alessandro F, Vladimir K, et al. Image denoising by sparse 3D transform-domain collaborative ltering [J]. IEEE Transactions on Image Processing, 2007, 16(8): 1-16.
[6] Zhang Kai, Zuo Wangmeng, Chen Yunjin, et al. Beyond a gaussian denoiser: residual learning of deep CNN for image denoising [J]. IEEE Transactions on Image Processing, 2017, 26(7): 3142-3155.
[7] Goodfellow I, Pouget-Abadie J, Mirza M, et al. Generative adversarial nets [C]//Neural Information Processing Systems (NIPS). Montreal:MIT Press, 2014: 2672-2680.
[8] Abdrrahman O,Lala O. Supervised deep convolutional generative adversarial networks[J]. Neurocomputing, 2021, 449(8):389-398.
[9] Choi K, Vania M, Kim S. Semi-Supervised learning for low-dose CT image restoration with hierarchical deep generative adversarial network (HD-GAN) [C]// IEEE 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). Berlin: IEEE, 2019: 2683-2686.
[10] Zhang Xuewen, Zhang Yunye, Yu Wenxin, et al. Semi-supervised learning with conditional GANs for blind generated image quality assessment [C]// International Conference on Neural Information Processing (ICONIP). Bali: LNCS, 2021: 482-493.
[11] Hu Bo, Tang Ye,Chang E, et al. Unsupervised learning for cell-level visual representation in histopathology images with generative adversarial networks [J]. IEEE Journal of Biomedical and Health Informatics, 2019, 23(3):1316-1328.
[12] Chen Jingwen, Chen Jiawei, Chao Hongyang, et al. Image blind denoising with generative adversarial network based noise modeling [C]//Computer Vision and Pattern Recognition (CVPR). Salt Lake City: IEEE, 2018: 3155-3164.
[13] Chen SongKui, Shi Daming, Muhammad S, et al. Image denoising with generative adversarial networks and its application to cell image enhancement[J]. IEEE Access, 2020, 8(4): 82819-82831.
[14] Mirza M, Osindero S. Conditional generative adversarial nets [EB/OL].https://arxiv.org/pdf/1411.1784.pdf,2014-11-06/2021-10-13.
[15] Arjovsky M, Chintala S, Bottou L. Wasserstein GAN [EB/OL]. https://arxiv.org/pdf/1701.07875.pdf, 2017-12-06/2021-10-13.
[16] Mao Xudong, Li Qing, Xie Haoran, et al. Least squares generative adversarial networks [C]//IEEE International Conference on Computer Vision (ICCV). Venice: IEEE, 2017: 17453045.
[17] Ledig C, Theis L, HuszÃr F, et al. Photo-realistic single image super-resolution using a generative adversarial network [C]//Computer Vision and Pattern Recognition (CVPR). Honolulu: IEEE, 2017: 105-114.
[18] Zhang Qi, Sun Jingzhang, Mok G. Low dose SPECT image denoising using a generative adversarial network [EB/OL]. https://arxiv.org/abs/1907.11944, 2019-07-27/2021-10-13.
[19] Yi Xin, Babyn P. Sharpness-aware low dose CT denoising using conditional generative adversarial network [J]. Journal of Digital Imaging, 2018, 31(5): 655-669.
[20] Yang Qingsong, Yan Pingkun, Zhang Yanbo, et al. Low-dose CT image denoising using a generative adversarial network with wasserstein distance and perceptual loss [J]. IEEE Transactions on Medical Imaging, 2018, 37(6): 1348-1357.
[21] Ran Maosong, Hu Jinrong, Chen Yang, et al. Denoising of 3-D magnetic resonance images using a residual encoder-decoder wasserstein generative adversarial network[J], Medical Image Physics, 2019, 55(7):165-180.
[22] Ma Yinjin, Wei Biao, Feng Peng, et al. Low-dose CT image denoising using a generative adversarial network with a hybrid loss function for noise learning [J]. IEEE Access, 2020, 8(4): 67519-67529.
[23] Chi Jianning, Wu Chengdong, Yu Xiaosheng, et al. Single low-dose CT image denoising using a generative adversarial network with modified U-Net generator and multi-level discriminator [J]. IEEE Access, 2020, 8(7):133470-133487.
[24] Xue Hengzhi, Teng Yueyang, Tie Changjun, et al. A 3D attention residual encoder-decoder least-square GAN for low-count PET denoising [J]. Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, 2020, 983(12): 164638.
[25] Tan Chuan, Zhu Jin, Lio P. Arbitrary scale super-resolution for brain MRI images [C]// IFIP Advnces in Information and Communication Technology (IFIPACT). Hangzhou: Springer, 2020: 165-176.
[26] Zhang Han, Goodfellow I, Metaxas D, et al. Self-attention generative adversarial networks [EB/OL]. https://arxiv.org/pdf/1805.08318.pdf, 2019-06-14/2021-10-13.
[27] Li Meng, Hsu W, Xie Xiaodong, et al. SACNN: self-attention convolutional neural network for low-dose CT denoising with self-supervised perceptual loss network [J]. IEEE Transactions on Medical Imaging, 2020, 39(7): 2289-2301.
[28] Jelmer M, Wolterink, T, Max A, et al. Generative adversarial networks for noise reduction in low-dose CT [J]. IEEE Transactions on Medical Imaging, 2017, 36(12): 2536-2545.
[29] Shan Hongming, Zhang Yi, Yang Qingsong, et al. 3-D convolutional encoder-decoder network for low-dose CT via transfer learning from a 2-D trained network [J]. IEEE Transactions on Medical Imaging, 2018, 37(6):1522-1534.
[30] Yang Linlin, Hong Shangguan, Zhang Xiong, et al. High-frequency sensitive generative adversarial network for low-dose CT image denoising [J]. IEEE Access, 2019, 8(12): 930-943.
[31] Wang Ziyuan, Wang Lidan, Duan Shukai, et al. An image denoising method based on deep residual GAN [J]. Journal of Physics Conference Series, 2020, 1550(3): 032127.
[32] Chen Hu, Zhang Yi, Kalra M, et al. Low-dose CT with a residual encoder-decoder convolutional neural network (RED-CNN) [J]. IEEE Transactions on Medical Imaging, 2017, 36(12): 2524-2535.
[33] Gu Jiuxiang, Wang Zhenhua, Kuen J, et al. Recent advances in convolutional neural networks [J]. Pattern Recognition, 2018, 77(5): 354-377.
[34] Cho K, Merrienboer B, Bahdanau D, et al. On the properties of neural machine translation: encoder-decoder approaches [EB/OL]. https://arxiv.org/pdf/1409.1259.pdf, 2014-10-07/2021-10-13.
[35] Ronneberger O, Fischer P, Brox T. U-Net: convolutional networks for biomedical image segmentation [C]// Medical Image Computing and Computer-Assisted Intervention (MICCAI). Munich: Springer, 2015:234-241.
[36] He Kaiming, Zhang Xiangyu, Ren Shaoqing, et al. Deep residual learning for image recognition [C]// Computer Vision and Pattern Recognition (CVPR). Las Vegas: IEEE, 2016: 16541111.
[37] Zhu Jin, Tan Chuan,Yang Junwei, et al. MIASSR: An approach for medical image arbitrary scale super-resolution [EB/OL]. https://arxiv.org/pdf/2105.10738.pdf, 2021-05-22/2021-10-13.
[38] Wang Zhou, Bovik A, Sheikh H, et al. Image quality assessment: from error visibility to structural similarity [J]. IEEE Transactions on Image Processing, 2014, 13(4): 600-612.
[39] Ge Rongjun, Yang Guanyu, Xu Chenchu. Stereo-correlation and noise-distribution aware ResVoxGAN for dense slices reconstruction and noise reduction in thick low-dose CT [C]// Medical Image Computing and Computer Assisted Intervention (MICCAI). Shenzhen: Springer, 2019: 328-338.
[40] Binit V, Siddhant R, Dorsa Z, et al. CT-scan denoising using a charbonnier loss generative adversarial network [J]. IEEE Access, 2021, 99(6): 1-1.
[41] Mok G, Zhang Qi, Sun Jingzhang. Comparison of projection-based and reconstruction-based low dose SPECT image denoising using a conditional generative adversarial network [C]// IEEE Nuclear Science Symposium & Medical Imaging Conference. Boston: IEEE, 2020: 10.1109.
[42] Zhao Kui, Zhou Long, Gao Size, et al. Study of low-dose PET image recovery using supervised learning with CycleGAN [J]. PLoS ONE, 2020, 15(9): e0238455.
[43] Du Qianqian, Qiang Yan, Yang Wenkai. DRGAN: a deep residual generative adversarial network for PET image reconstruction [J]. Let Image Processing, 21 May, 2020 [Epub ahead of print].
[44] Yu Aihui, Liu Xiaoming, Wei Xiangkai, et al. Generative adversarial networks with dense connection for optical coherence tomography images denoising [C]//International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI). Beijing: IEEE, 2018:1-5.
[45] Dong Zhao, Liu Guoyan, Ni Guangming, et al. Optical coherence tomography image denoising using a generative adversarial network with speckle modulation [J]. Jornal of Biophotonics, 2020, 13(4): e201960135.
[46] Chen Zailiang, Zeng Ziyang, Shen Hailan, et al. DN-GAN: denoising generative adversarial networks for speckle noise reduction in optical coherence tomography images [J]. Biomedical Signal Processing and Control, 2020, 55:101632.
[47] Guo Yang, Wang Kang, Yang Suhui, et al. Structure-aware noise reduction generative adversarial network for optical coherence tomography image (OMIA) [C]// International Workshop on Ophthalmic Medical Image Analysis. Shenzhen: Springer, 2019: 9-17.
[48] Liang Kaicheng, Liu Xinyu, Chen Si, et al. Resolution enhancement and realistic speckle recovery with generative adversarial modeling of micro-optical coherence tomography [J]. Biomedical Optics Express, 2020, 11(12): 7236-7236.
[49] Izabela H, Johannes C, Oliver S, et al. METGAN: Generative tumour inpainting and modality synthesis in light sheet microscopy [C]// Winter Conference on Applications of Computer Vision (WACV). Waikoloa: IEEE, 2022:3230-3240.